© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8413
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and arguments related to clauses and verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    placement or order of words

    np_acts-logits-general · gemini-2.0-flash

    positional relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.73
    ")){
    -0.66
    sizeCache
    -0.66
    printStackTrace
    -0.64
     Symp
    -0.63
    ')['
    -0.61
    styleType
    -0.61
    AndroidJUnit
    -0.59
    __':
    -0.59
    modelBuilder
    -0.58
    POSITIVE LOGITS
     preceding
    1.23
     preceded
    1.16
     precede
    1.06
     followed
    1.03
     precedes
    0.99
     précé
    0.90
     preced
    0.82
     before
    0.81
     after
    0.80
    preced
    0.77
    Activations Density 0.840%

    No Known Activations